Inspur Information (浪潮信息) launched the Yuannao (元脑) SD200 Ultra supernode AI server using domestic AI chips.

Inspur Information (浪潮信息) introduced the Yuannao (元脑) SD200 Ultra at the 2026 Artificial Intelligence Computing Conference (2026 人工智能计算大会), identified as AICC2026, on September 21. Financial_Express reports that the supernode AI server uses domestic AI chips, without naming the chip supplier or model.

According to the launch description, a single system can run the 2.8-trillion-parameter Kimi K3 model. The report also claims token-generation latency broke through the 5.85-millisecond threshold (Token 生成时延首次突破 5.85 毫秒), but provides no benchmark configuration, concurrency level, precision, or detailed latency definition.

The single-system claim refers to the announced supernode server, not a single chip or GPU. Inspur Information also launched the Yuannao (元脑) HC2000 heterogeneous-compute unit (多元算力机组), although the message supplies no hardware configuration, price, power rating, or shipment schedule for either product.